Boundary Matters: A Bi-Level Active Finetuning Framework

arXiv:2403.10069v1 Announce Type: new
Abstract: The pretraining-finetuning paradigm has gained widespread adoption in vision tasks and other fields, yet it faces the significant challenge of high sample annotation costs. To mitigate this, the concept of active finetuning has emerged, aiming to select the most appropriate samples for model finetuning within a limited budget. Traditional active learning methods often struggle in this setting due to their inherent bias in batch selection. Furthermore, the recent active finetuning approach has primarily concentrated on …

abstract adoption annotation arxiv budget challenge concept costs cs.ai cs.cv fields finetuning framework paradigm pretraining sample samples tasks type vision